Skip to content
View albert-lv's full-sized avatar
7 followers · 10 following

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Block or report albert-lv

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
albert-lv/README.md

Hi, I'm Albert ๐Ÿ‘‹

Typing SVG

๐Ÿ”ฌ What I Do

I build AI Agents, Developer Tools, and Reinforcement Learning systems โ€” with a soft spot for TUIs, code analysis, and open-source education.

"Building the tools that let agents build the future."

๐Ÿš€ Projects

โญ Featured: the nano series

Minimal, readable implementations of agent loops & harness engineering โ€” real systems, kept small enough to read in an evening. Paired chapter-by-chapter with the harness-101 course. ๐ŸŒ nano-harness.github.io

Project Language Description
nano-agent Go A minimal AI coding assistant โ€” agent loop, tools, context management, swarm multi-agent
nano-symphony TypeScript Lightweight orchestration service for running coding agents on tracked issues
nano-cloud Go Distributed execution for agents โ€” gateway/worker architecture for agent fleets

๐Ÿค– AI / Agent Systems

Project Language Description Stars
OpenAgora Python Open-source rollout, verification & trajectory plane for agentic RL โญ 3
evernote-ai HTML AI assistant for Evernote with RAG, semantic search & weekly summaries โ€”

๐Ÿ› ๏ธ Developer Tools

Project Language Description Stars
designing-tuis Skill Terminal UI design system โ€” screenshot-to-code for TUIs โญ 17
code-parser Python tree-sitter based Java code analysis for Spring/Swagger validation โ€”

๐Ÿ“š Knowledge & Education

Project Description
LLM-primer Bilingual, multi-tier LLM knowledge base (community-PR driven)
harness-101 ไปŽ้›ถๆž„ๅปบ AI Agent ไธŽ Harness Engineering ๅฎžๆˆ˜่ฏพ็จ‹๏ผˆ12 ๅ› ็ด ๆ–นๆณ•่ฎบ๏ผŒ้…ๅฅ—ๅฏ่ฟ่กŒๅฎž็Žฐ่ง nano ็ณปๅˆ—๏ผ‰
agent-tips Daily AI agent tool tips (Claude Code, Kimi Code, Cursor, Windsurf, etc.)
interview-prep Daily algorithm problems & coding interview preparation

๐Ÿงฎ Language & Compiler

Project Language Description
calculator-LL1 Java Simple calculator using LL(1) parsing algorithm
calculator-LR1 Java Simple calculator using LR(1) parsing algorithm

๐ŸŒ Web

Project Language Description
openagora-website HTML Official landing page for OpenAgora

๐Ÿง‘โ€๐Ÿ’ป Tech Stack

Languages

Go Rust Python TypeScript Java Swift Shell

Domains

  • ๐Ÿค– AI Agent & RL โ€” Agentic systems, GRPO/verifiable RL, tool harness, coding agents

  • ๐Ÿ› ๏ธ Developer Experience โ€” TUI design, code analysis, impact tracking, virtual filesystems

  • ๐Ÿ“ฆ Infrastructure โ€” Distributed orchestration, MCP servers, SSE/WebSocket systems

  • ๐ŸŽจ Open Source Education โ€” Courseware, knowledge bases, daily tips

  • ๐Ÿ’ก Sharing agent tips & tools at agent-tips

"Open source is not just about code โ€” it's about building the commons."

Pinned Loading

  1. OpenAgora OpenAgora Public

    Open-source rollout, verification, and trajectory plane for agentic reinforcement learning.

    Python 3

  2. designing-tuis designing-tuis Public

    Use when designing terminal user interfaces, building TUI welcome screens / dashboards / wizards / CLI launch screens, replicating TUI app layouts from screenshots (lazygit, k9s, btop, etc.), or itโ€ฆ

    17 2

  3. harness-101 harness-101 Public

    Hands-on course: Build AI Agents and Harness Engineering from Scratch

    HTML

  4. nano-harness/nano-agent nano-harness/nano-agent Public

    A minimal AI coding assistant in Go โ€” agent loop, modular tools, swarm multi-agent, TUI + daemon modes. Part of the nano series.

    Go

  5. nano-harness/nano-cloud nano-harness/nano-cloud Public

    Distributed execution for agents โ€” gateway/worker architecture for running agent fleets in isolated Docker runtimes. Part of the nano series.

    Go

  6. nano-harness/nano-symphony nano-harness/nano-symphony Public

    Lightweight orchestration service for running coding agents on tracked issues โ€” plan runs, isolated workspaces, MCP integration, web dashboard. Part of the nano series.

    TypeScript